| any_to_any.html | 27.7 kB | | 8baf005a |
| any_to_any.md | 4.85 kB | | 870fe9f3 |
| asr.html | 72.3 kB | | 55fd747f |
| asr.md | 14.5 kB | | 635b5ab3 |
| audio_classification.html | 66 kB | | ac60419c |
| audio_classification.md | 11.9 kB | | 1ef5da19 |
| audio_text_to_text.html | 69.9 kB | | 1da6bee4 |
| audio_text_to_text.md | 12.2 kB | | 5f278a9c |
| document_question_answering.html | 109 kB | | f78147c5 |
| document_question_answering.md | 24 kB | | 147e5a69 |
| idefics.html | 69.5 kB | | 0b651465 |
| idefics.md | 18.9 kB | | df6ccca7 |
| image_captioning.html | 50.5 kB | | dbe4be8c |
| image_captioning.md | 7.29 kB | | e7306158 |
| image_classification.html | 61.8 kB | | a08774a7 |
| image_classification.md | 10.6 kB | | 31ba7d73 |
| image_feature_extraction.html | 31.2 kB | | 307146a8 |
| image_feature_extraction.md | 4.49 kB | | b1f5e2ae |
| image_text_to_text.html | 62.1 kB | | 20cf2965 |
| image_text_to_text.md | 16.6 kB | | dee75285 |
| instance_segmentation.html | 72.5 kB | | ea43742a |
| instance_segmentation.md | 17.3 kB | | b888780d |
| keypoint_detection.html | 26.6 kB | | 53658549 |
| keypoint_detection.md | 5.21 kB | | 57820119 |
| keypoint_matching.html | 24.6 kB | | e14b9e5b |
| keypoint_matching.md | 4.4 kB | | 8c36cf52 |
| knowledge_distillation_for_image_classification.html | 31.8 kB | | d367cd6c |
| knowledge_distillation_for_image_classification.md | 7.79 kB | | 48932cb5 |
| language_modeling.html | 63.6 kB | | c73f8c78 |
| language_modeling.md | 13.8 kB | | ba757bf5 |
| mask_generation.html | 81.5 kB | | 2e4cafaf |
| mask_generation.md | 17.1 kB | | 720016f1 |
| masked_language_modeling.html | 64.4 kB | | 185bcfda |
| masked_language_modeling.md | 13.4 kB | | de20325d |
| monocular_depth_estimation.html | 30.6 kB | | 1ebec60a |
| monocular_depth_estimation.md | 5.82 kB | | a6bda375 |
| multiple_choice.html | 52.2 kB | | 944a5c18 |
| multiple_choice.md | 9.21 kB | | 2f73573f |
| object_detection.html | 93.5 kB | | 84258dd7 |
| object_detection.md | 22.8 kB | | a82fb4b5 |
| prompting.html | 37.8 kB | | f69ce951 |
| prompting.md | 13.4 kB | | 87d4c00c |
| question_answering.html | 55.7 kB | | 3810775b |
| question_answering.md | 11.1 kB | | 0aa2f4ab |
| semantic_segmentation.html | 116 kB | | 18102827 |
| semantic_segmentation.md | 23 kB | | b128a3eb |
| sequence_classification.html | 54.7 kB | | b134f059 |
| sequence_classification.md | 10.1 kB | | 93031884 |
| summarization.html | 61.1 kB | | 06d9490e |
| summarization.md | 17.4 kB | | 4cab0020 |
| text-to-speech.html | 130 kB | | ab3f6a2a |
| text-to-speech.md | 23.6 kB | | f0d23557 |
| token_classification.html | 74.2 kB | | 83548c9f |
| token_classification.md | 13.7 kB | | 9fdbd835 |
| training_vision_backbone.html | 36.8 kB | | ff9c39a3 |
| training_vision_backbone.md | 8.7 kB | | dee8d0aa |
| translation.html | 54.8 kB | | c831090c |
| translation.md | 10 kB | | 4091bacf |
| video_classification.html | 91.4 kB | | d5e2b1d6 |
| video_classification.md | 20.8 kB | | 7749ebb2 |
| video_text_to_text.html | 26 kB | | 94875d8d |
| video_text_to_text.md | 5.91 kB | | 35065842 |
| visual_document_retrieval.html | 27.7 kB | | 1599ac32 |
| visual_document_retrieval.md | 5.58 kB | | c8b7ee4e |
| visual_question_answering.html | 71.5 kB | | 8e90277a |
| visual_question_answering.md | 14.8 kB | | 17cc505b |
| zero_shot_image_classification.html | 30.5 kB | | a7faa6ba |
| zero_shot_image_classification.md | 5.05 kB | | 2b9f3d07 |
| zero_shot_object_detection.html | 58.6 kB | | b8e0f118 |
| zero_shot_object_detection.md | 10.3 kB | | 0c085bd3 |
